Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Nested Named Entity Recognition as Single-Pass Sequence Labeling

  • Muñoz-Ortiz, Alberto
  • Vilares, David
  • Corro, Caio
  • Gómez-Rodríguez, Carlos
Presented at: Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Suzhou, China, November 4th to November 9th, 2025., [Abstract]: We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to straightforward token classification. By combining these constituency linearizations with pretrained encoders, our method captures nested entities while performing exactly n tagging actions. Our approach achieves competitive performance compared to less efficient systems, and it can be trained using any off-the-shelf sequence labeling library., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114, France. Agence nationale de la recherche; ANR-23-IAS1-0004, France. Agence nationale de la recherche; ANR-23-CE23-0005
RUC. Repositorio da Universidade da Coruña
Publicación Proyecto fin de carrera (BachelorThesis)

Dinámicas de entrenamiento para la caracterización de datos sintéticos en NLP

  • Lago Pato, Irene
[Resumen] La creciente utilización de los Large Language Models (LLMs) para la generación de datos sintéticos ha abierto nuevas posibilidades para reducir la dependencia de la anotación manual en tareas de Procesamiento del Lenguaje Natural (NLP). Sin embargo, su utilidad depende de su capacidad para representar la diversidad y complejidad presentes en datos humanos, lo que hace necesario desarrollar metodologías que permitan caracterizarlos y evaluarlos. En este trabajo se propone un marco de análisis basado en las dinámicas de entrenamiento de modelos supervisados para estudiar las propiedades de los datos sintéticos. Para ello, se generan conjuntos de datos correspondientes a distintas tareas de NLP mediante diferentes modelos de lenguaje y estrategias de generación, comparando su comportamiento con datos de referencia elaborados por humanos. Además, se estudia la robustez del marco propuesto utilizando distintos modelos para extraer las dinámicas de entrenamiento, con el objetivo de comprobar si la caracterización obtenida se mantiene estable independientemente del modelo empleado. Finalmente, se analiza cómo diferentes estrategias de selección de datos basadas en estas dinámicas afectan al entrenamiento de modelos supervisados. Los resultados muestran que este marco permite identificar diferencias relevantes entre datos sintéticos y humanos, así como analizar la influencia que ejercen la familia y el tamaño del LLM sobre las características de los datos generados. De este modo, este Trabajo de Fin de Grado busca contribuir al estudio de la calidad de los datos generados por LLMs en tareas críticas de NLP, evaluando hasta qué punto dichos datos pueden complementar o incluso sustituir el esfuerzo humano y definiendo una metodología para evaluar estos corpus e identificar las muestras más valiosas para el entrenamiento de modelos., [Abstract] The increasing use of Large Language Models (LLMs) for synthetic data generation has opened new opportunities to reduce the reliance on manual annotation in Natural Language Processing (NLP) tasks. However, their usefulness depends on their ability to capture the diversity and complexity of human-generated data, making it necessary to develop methodologies for their characterization and evaluation. This work proposes an analysis framework based on the training dynamics of supervised models to study the properties of synthetic data. To this end, datasets corresponding to different NLP tasks are generated using various language models and generation strategies, and their behavior is compared with that of human-created reference datasets. Furthermore, the robustness of the proposed framework is evaluated by employing different models to extract training dynamics, with the aim of determining whether the resulting characterization remains stable regardless of the underlying model. Finally, the impact of different data selection strategies based on these dynamics on the training of supervised models is analyzed. The results show that this framework can effectively identify relevant differences between synthetic and human-generated data, while also revealing the influence of LLM family and model size on the characteristics of the generated data. Thus, this Final Degree Project aims to contribute to the study of the quality of data generated by LLMs in critical NLP tasks, by analyzing the extent to which such data can complement or even replace human effort, and by defining a methodology to evaluate these corpora and identify the most valuable samples for model training., Este trabajo se ha desarrollado en el marco del proyecto (GAP; PID2022-139308OA-I00) financiado por MICIU/AEI/10.13039/501100011033 y por FEDER, UE. Asimismo, este proyecto de investigación ha sido posible gracias al acceso concedido por el Centro de Supercomputación de Galicia (CESGA) a su infraestructura de supercomputación. El supercomputador FinisTerrae III y su sistema de almacenamiento permanente de datos han sido financiados por el Plan de Recuperación, Transformación y Resiliencia 2021 de NextGenerationEU, ICT2021-006904, así como por el Programa Operativo Plurirregional de España 2014-2020 del Fondo Europeo de Desarrollo Regional (FEDER), ICTS-2019-02-CESGA-3, y por el Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia del Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 (Subprograma Estatal de Infraestructuras Científicas y Técnicas y Equipamiento) del FEDER, CESG15-DE-3114., Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114, Traballo fin de grao (UDC.FIC). Intelixencia Artificial. Curso 2025/2026
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

FABaS: Flow Activity-Biased Importance Sampling for Deep Learning Image-Based Flow Compression and Prediction

  • Mures, Omar A.
  • Dopazo García, Abrahan
  • Cid Montoya, Miguel
[Abstract]: Flow field compression is a key milestone for the feasible implementation of deep learning (DL) models at scale and the efficient storage of the flow datasets required for their training. Sampling strategies represent a fundamental step in vision-based compression techniques, directly conditioning both model accuracy and compression ratios. Their main objective is to accurately capture all necessary flow features for reproducing the phenomena of interest, which typically involves extracting wind-induced forces while simultaneously resolving flow characteristics in the near and far wakes. However, accurately identifying flow information in those regions requires conflicting sampling criteria. To address this challenge, this study proposes an importance sampling strategy guided by flow activity to automatically identify and focus on high-activity regions within the flow domain, combining signed distance functions (SDFs) and vorticity fields. The proposed flow activity-biased importance sampling (FABaS) method achieves near-lossless compression ratios of 37 718:1 while guaranteeing accurate reproduction of flow features, with a mean absolute percentage error (MAPE) of 0.063 %, for precise surface force extraction in the boundary layer region and far wake. Consequently, this technique is a powerful tool for deep learning compression and prediction of flow field data. The FABaS code is available on GitHub., This paper is based upon work supported by the National Science Foundation (NSF) under Grant No. CMMI-2503131. Miguel Cid Montoya was also supported by the new faculty start-up funds provided by Clemson University. Omar A. Mures acknowledges partial support by Xunta de Galicia (ED431B 2025/21) and the Centre for ICT Research (CITIC) that receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia (Ref. ED431G 2023/01). This research project was made possible through the access granted by the Galicia Supercomputing Center (CESGA) to its infrastructure. It has been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the European Regional Development Fund (ERDF), ICTS-2019- 02-CESGA-3, and the state subprogramme for scientific and technical infrastructures and equipment CESG15-DE-3114, Estados Unidos. National Science Foundation; 2503131, Xunta de Galicia; ED431B 2025/21, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ICTS-2019- 02-CESGA-3, Xunta de Galicia; CESG15-DE-3114
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Facilitando el aprendizaje en bioinformática y reposicionamiento de fármacos mediante una plataforma web intuitiva enfocada en el análisis de resultados

  • Mouzo Quiza, Raúl
  • Fernández-Edreira, Diego
  • Fernández-Lozano, Carlos
Poster presentado en: XXXI Jornadas sobre la Enseñanza Universitaria de la Informática (JENUI 2025). Valladolid, 9-11 de julio de 2025. Traballos presentados dispoñibles en: https://aenui.org/actas/indice_e.html#anio2025, [Resumen] Se propone una plataforma web vanguardista diseñada para facilitar experimentos de reposicionamiento de fármacos, que permite a los estudiantes la visualización de estructuras tridimensionales de proteína y fármaco así como su acoplamiento espacial. Este recurso educativo ofrece acceso inmediato a información esencial sobre genes, proteínas y sus estructuras, y fármacos, ejecutándose de manera eficiente sobre un cluster de supercomputación. Sobresale en su capacidad para facilitar la interacción de los estudiantes con datos complejos sin la necesidad de programación preliminar, eliminando barreras técnicas y permitiendo un enfoque centrado en el análisis y la interpretación de resultados. La herramienta se alinea eficazmente con métodos de enseñanza activa y aprendizaje basado en proyectos, proporcionando a los estudiantes de biología, química e informática una experiencia práctica. Destaca por su carácter novedoso y original, integrando tecnologías avanzadas en un entorno accesible para la docencia. Su aplicabilidad se ve potenciada por una interfaz intuitiva y recursos complementarios disponibles en línea., [Abstract] A cutting-edge web platform is proposed, designed to facilitate drug repositioning experiments, enabling students to visualize three-dimensional structures of proteins and drugs, as well as their spatial docking. This educational resource provides immediate access to essential information about genes, proteins, their structures, and drugs, running efficiently on a supercomputing cluster. It excels in its ability to facilitate student interaction with complex data without the need for prior programming, eliminating technical barriers and allowing a focus on analysis and result interpretation. The tool effectively aligns with active teaching methods and project-based learning, offering biology, chemistry, and computer science students a hands-on experience. It stands out for its innovative and original nature, integrating advanced technologies within an accessible teaching environment. Its applicability is enhanced by an intuitive interface and complementary online resources., Este trabajo se desarrolló gracias al acceso concedido por el Centro de Supercomputación de Galicia (CESGA) a sus infraestructuras de supercomputación. El Superordenador FinisTerrae III y su sistema de almacenamiento permanente de datos han sido financiados por el NextGeneration EU 2021 Plan de Recuperación, Transformación y Resiliencia, ICT2021-006904, y también con el Programa Operativo Plurirregional de España 2014-2020 del FEDER (Fondo Europeo de Desenvolvemento Rexional), ICTS-2019-02-CESGA3, y con el Programa Estatal de Fomento da Investigación Científica y Técnica de Excelencia del Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 (1) Subprograma estatal de infraestructuras científicas y técnicas y equipamiento del FEDER, CESG15-DE-3114, y finalmente al Programa Europeo Interreg VI-B Sudoe 2021-2027 (S1/1.1/P0033) cofinanciado con fondos FEDER (Fondo Europeo de Desenvolvemento Rexional)., Xunta de Galicia; ICTS-2019- 02-CESGA-3, https://aenui.org/actas/pdf/JENUI_2025.pdf
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Bringing Emerging Architectures to Sequence Labeling in NLP

  • Ezquerro, Ana
  • Gómez-Rodríguez, Carlos
  • Vilares, David
Presented at: 19th Conference of the European Chapter of the Association for Computational Linguistics, March 24–29, 2026, Rabat, Morocco, [Abstract]: Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks., We acknowledge grants GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). This research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Analysis of federated learning on non-independent and identically distributed sleep data

  • Anido Alonso, Adriana
  • Álvarez-Estévez, Diego
[Abstract]: Objective. We investigate the application of federated learning (FL) across heterogeneous, non-independent and identically distributed (non-IID) sleep data. We evaluate three algorithms-federated stochastic gradient descent, federated averaging, and federated proximal (FedProx)-in a realistic setting where non-IID characteristics arise from distinct sensor configurations, varying acquisition protocols, and diverse patient populations across independent sleep cohort datasets. Approach. We employ a dual-layered evaluation framework. First, we systematically analyze the impact of local training epochs and aggregation schemes (weighted and unweighted) on model convergence. Second, we introduce and adapt a generalized sub-sampling strategy designed to mitigate model drift caused by heterogeneous data distribution and volume imbalances across participating clients. To ensure robust external generalization, our evaluation utilizes six independent databases in a leave-one-database-out cross-validation scheme. Main results. Our analysis has evidenced that increasing the number of local training epochs adversely affects performance across all evaluated federated schemes. This confirms that extended local training exacerbates client drift, hindering global convergence. Furthermore, weighted aggregation consistently under-performs unweighted approaches, suggesting that disproportionate client contributions bias the global data representation. While the inclusion of a proximal term partially mitigates this instability by constraining local updates, the proposed sub-sampling strategy proves most effective. This approach yields consistent generalization results across all algorithms and minimizes performance downgrading, while significantly reducing computational overhead. Significance. This work addresses critical privacy concerns in centralized automated sleep staging by validating FL in realistic, multi-center scenarios. We provide evidence that decentralized strategies can achieve performance comparable to centralized methods, effectively overcoming data silos. Ultimately, this approach enables robust collaborative training while strictly maintaining data privacy-a fundamental requirement for widespread clinical implementation., This study has been supported by project RYC2022-038121-I, funded by MCIN/AEI/10.13 039/50110 0011033 and European Social Fund Plus (ESF+), project PID2023-147422OB-I00 funded by MCIU/AEI/10.13039/501100011033 and by the European FEDER program, and project ED431F 2025/35 funded by Xunta de Galicia. Authors wish to acknowledge the support received from Universidade da Coruña and Centro de Investigación de Galicia ‘CITIC’, center accredited for excellence within the Galician University System and a member of the CIGUS Network. CITIC receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia and it is co-financed by the EU through the FEDER Galicia 2021-27 operational program ED431G 2023/01. Furthermore, this research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114, Xunta de Galicia; ED431F 2025/35, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114